pith:CH5V77TW
HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation
Cognitive personas synthesizing humor data let a 7B model match or beat much larger LLMs at comedy.
arxiv:2604.09629 v2 · 2026-03-19 · cs.CL
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{CH5V77TW4BFNHBEX7ACUJVQKY4}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
our 7B model significantly outperforms larger instruction-tuned baselines and achieves performance competitive with state-of-the-art proprietary models. We find that cognitive-driven data curation is far more critical than alignment algorithms or model scale for humor generation.
The humor data synthesized using the six cognitive personas through the Mixture-of-Thought approach provides a high-quality, diverse training signal that effectively improves the model's humor generation capabilities beyond what standard methods achieve.
A 7B LLM fine-tuned on humor data generated via six cognitive personas and Mixture-of-Thought outperforms larger instruction-tuned baselines and competes with proprietary models.
Formal links
Receipt and verification
| First computed | 2026-05-29T01:05:09.218698Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
11fb5ffe76e04ad38497f80544d60ac73f0b103bce0d44165748bf69ec58a0f3
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/CH5V77TW4BFNHBEX7ACUJVQKY4 \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 11fb5ffe76e04ad38497f80544d60ac73f0b103bce0d44165748bf69ec58a0f3
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "bbae0302de87646da20dceb2d7ce21d7d84e15dbedb1bf446984145ce89be050",
"cross_cats_sorted": [],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.CL",
"submitted_at": "2026-03-19T13:12:53Z",
"title_canon_sha256": "a70fe9a889fc1b56c29469a1aecb5c4cec6f569778a619b78ca907d659a852eb"
},
"schema_version": "1.0",
"source": {
"id": "2604.09629",
"kind": "arxiv",
"version": 2
}
}